1.College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116 2.Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing,Fuzhou University, Fuzhou 350116 3.College of Electronics and Information Science, Fujian Jiang-xia University, Fuzhou 350108 4.Key Laboratory of Network Data Science and Technology, Chinese Academy of Sciences, Beijing 100190
Abstract：In the current memory network model, the words of the context are independent of each other, and the influence of word order information on microblog sentiment is not taken into account. Therefore, a perspective level microblog sentiment classification method based on convolutional memory network is proposed. In the method, memory network can effectively model the semantic relation between the query and the text. Consequently, the view and the text are abstracted via this property. Furthermore, the word order in context is extended by convolutional operation. Then, the result is utilized to capture the attention signals of different terms in context for the weighted representation of text. Experimental results on three public datasets indicate that the proposed method achieves higher accuracies and Macro-F1 values compared with other methods.
[1] PANG B, LEE L L. Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2008, 2(1/2): 1-135. [2] LIU B. Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies, 2012, 5(1): 1-167. [3] JIANG L, YU M, ZHOU M, et al. Target-Dependent Twitter Sentiment Classification // Proc of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2011, I: 151-160. [4] YU J X, ZHA Z J, WANG M, et al. Aspect Ranking: Identifying Important Product Aspects from Online Consumer Reviews // Proc of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2011, I: 1496-1505. [5] WAGNER J, ARORA P, CORTES S, et al. DCU: Aspect-Based Polarity Classification for SemEval Task 4 // Proc of the 8th International Workshop on Semantic Evaluation. Stroudsburg, USA: ACL, 2014: 223-229. [6] KIM Y. Convolutional Neural Networks for Sentence Classification[C/OL]. [2017-03-30]. https://arxiv.org/pdf/1408.5882.pdf. [7] SOCHER R, LIN C C, NG A Y, et al. Parsing Natural Scenes and Natural Language with Recursive Neural Networks // Proc of the 28th International Conference on Machine Learning. Madison, USA: Omnipress, 2011: 129-136. [8] HOCHREITER S, SCHMIDHUBER J. Long Short-Term Memory. Neural Computation, 1997, 9(8): 1735-1780. [9] DONG L, WEI F R, TAN C Q, et al. Adaptive Recursive Neural Network for Target-Dependent Twitter Sentiment Classification[C/OL]. [2017-03-30]. http://ir.hit.edu.cn/~dytang/paper/ACL14-short-dongli/14ACL-short-dongli.pdf. [10] VO D T, ZHANG Y. Target-Dependent Twitter Sentiment Classification with Rich Automatic Features // Proc of the 24th International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2015: 1347-1353. [11] TANG D Y, QIN B, FENG X C, et al. Effective LSTMs for Target-Dependent Sentiment Classification[C/OL]. [2017-03-30]. https://arxiv.org/pdf/1512.01100.pdf. [12] LAKKARAJU H, SOCHER R, MANNING C. Aspect Specific Sentiment Analysis Using Hierarchical Deep Learning[C/OL].[2017-03-30]. http://www.dlworkshop.org/58.pdf?attredireets=0. [13] NGUYEN T H, SHIRAI K. PhraseRNN: Phrase Recursive Neural Network for Aspect-Based Sentiment Analysis // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2015: 2509-2514. [14] LUONG M T, PHAM H, MANNING C D. Effective Approaches to Attention-Based Neural Machine Translation[C/OL].[2017-03-30]. https://arxiv.org/pdf/1508.04025.pdf. [15] TANG D, QIN B, LIU T. Aspect Level Sentiment Classification with Deep Memory Network[C/OL]. [2017-03-30]. https://arxiv.org/pdf/1605.08900.pdf. [16] RUSH A M, CHOPRA S, WESTON J. A Neural Attention Model for Abstractive Sentence Summarization[C/OL]. [2017-03-30]. https://arxiv.org/pdf/1509.00685.pdf. [17] DU J C, XU R F, HE Y L, et al. Stance Classification with Target-Specific Neural Attention // Proc of the 26th International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2017: 3988-3994. [18] PONTIKI M, GALANIS D, PAVLOPOULOS J, et al. SemEval-2014 Task 4: Aspect Based Sentiment Analysis // Proc of the 8th International Workshop on Semantic Evaluation. Stroudsburg, USA: ACL, 2014: 27-35. [19] SUKHBAATAR S, SZLAM A, WESTON J, et al. End-to-End Memory Networks[C/OL]. [2017-03-30]. https://arxiv.org/pdf/1503.08895.pdf. [20] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed Representations of Words and Phrases and Their Compositionality // BURGES C J C, BOTTOU L, WELLING M, et al., eds. Advances in Neural Information Processing Systems 26. Cambridge, USA: The MIT Press, 2013: 3111-3119. [21] GUI L, HU J N, HE Y L, et al. A Question Answering Approach for Emotion Cause Extraction // Proc of the 14th International Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2017:1594-1603. [22] PENNINGTON J, SOCHER R, MANNING C D. Glove: Global Vectors for Word Representation[C/OL]. [2017-03-30]. https://nlp.stanford.edu/pubs/glove.pdf. [23] TANG D, WEI F R, YANG N, et al. Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification[C/OL]. [2017-03-30]. http://anthology.aclweb.org/P/P14/P14-1146.pdf. [24] SOCHER R, CHEN D Q, MANNING C D, et al. Reasoning with Neural Tensor Networks for Knowledge Base Completion // BURGES C J C, BOTTOU L, WELLING M, et al., eds. Advances in Neural Information Processing Systems 26. Cambridge, USA: The MIT Press, 2013: 926-934. [25] SUN Y, LIN L, TANG D, et al. Modeling Mention, Context and Entity with Neural Networks for Entity Disambiguation // Proc of the 24th International Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2015: 1333-1339.
2018, Vol. 31 
